Quantitative methods (01) - Introduction
-
Non-scientific Methods
-
Intuition/belief
- just opinion
-
Consensus
-
Just because most people accept something as true, doesn’t mean it is true.
- just opinion
-
-
Authority
- just opinion
-
Casual observation
-
People just aren’t very good at observing, we tend to selectively observe and remember things that agree with our beliefs.
- biased/flawed
-
-
Informal logic
- biased/flawed
graph RL B[Evidence] --?--> A[Opinion]
-
-
Scientific Methods
-
Principles
-
empirically testable
- observations—data
-
replicable
-
objective
- clear assumptions/concepts/clear procedures
-
transparent
- replicated by anyone
- publicly shared
-
falsifiable
-
Logically consistent
- hypothesis internally coherent
- conclusion logically consistent
-
-
-
Scientific Claims
-
Observation
- accurate/inaccurate
- doesn’t describe/explain general relation
-
Hypothesis
- describes/explains pattern, general relation
- not certain/strongly supported: Law
-
Theory
- overarching explanation of many related phenomena
- **closest to certainty, but not necessarily true! **
-
-
A short history of Science
-
Classical Period
- Greek Scholars(390 B.C.-350 B.C.)
- Plato
- realist/rationalist/理性未知论者/形而上学
- the external world and the objects in it are imperfect reflections or shadows of ideal forms.
- knowledge about the ideal forms can only be gained through reasoning.
- Aristotle
- realist/empiricist/理性经验主义者
- reality is the physical world.
- we can use senses and observations to gain knowledge.
- Logic to explain the nature/observation
- syllogism三段论(A=B,B=C; A=C)
- starting premises needed!!!
- Plato
- Prelude of Enlightenment
- Systematic observation and Experimentation by Arabic Scholars
- Induction and Deduction by Grosseteste and Roger Bacon
- Printing Press
- Heliocentric model (日心说) by Copernicus and Galileo Galilei.
- Greek Scholars(390 B.C.-350 B.C.)
-
Enlightenment
-
Galileo Galilei
- the father of modern science
-
Rene Descartes—理性主义
-
Cogito, ergo sum.(he thought and therefore he must exist.我思故我在。)
- we only know the true nature of the world through reasoning.
-
-
Francis Bacon—经验主义
- The father of empiricism
- Inductive methods(From observations to explanations)
-
David Hume
- Skepticism
- only sensory data as a source of knowledge
- the true nature of reality consists only of the features of objects
- Problem of induction: conclusive verification? = impossible to know anything
-
German Idealism—Kant
-
-
Modern Science
-
-
Logical Positivism
- Science = study of meaningful (verifiable) statements
- Analytic statements
- like definitions
- a prior—don’t depend on state of the world
- Synthetic statements
- depend on state of the world
- a posteriori— verified through observation
- publicly accessible
- problem of induction==> confirmation criterion
- Analytic statements
- Science = study of meaningful (verifiable) statements
-
逻辑实证主义以经验为根据,以逻辑为工具,进行推理,用概率论来修正结论,但他们否认了感性认识的积极作用,是真正的理性主义。
- a statement is meaningful only if it’s falsifiable.
- risky experiments—maximize chance to falsify
-
Paradigm Shift
-
-
Hypothetico-deductive Method
-
According to it, scientific inquiry proceeds by formulating a hypothesis in a form that can be falsifiable, using a test on observable data where the outcome is not yet known. A test outcome that could have and does run contrary to predictions of the hypothesis is taken as a falsification of the hypothesis. A test outcome that could have, but does not run contrary to the hypothesis corroborates the theory. It is then proposed to compare the explanatory value of competing hypotheses by testing how stringently they are corroborated by their predictions.
-
Example
-
One example of an algorithmic statement of the hypothetico-deductive method is as follows:[1]
1. Use your experience: Consider the problem and try to make sense of it. Gather data and look for previous explanations. If this is a new problem to you, then move to step 2.
2. Form a conjecture (hypothesis): When nothing else is yet known, try to state an explanation, to someone else, or to your notebook.
3. Deduce predictions from the hypothesis: if you assume 2 is true, what consequences follow?
4. Test (or experiment): Look for evidence (observations) that conflict with these predictions in order to disprove 2. It is a logical error to seek 3 directly as proof of 2. This formal fallacy is called affirming the consequent.[2]
-
-
-
-
Empirical adequacy
-
observation required
-
unoberservables allowed
-
Scientific claim is ‘true’ only as far as the observables go
-
-
-
-
-
Epistemology 认识论
-
Ontology—Study of being
-
What is there to know?
-
Two types of questions:
- existence of external world(客观世界是否存在)
- existence of particulars&universals
- Particulars(殊相):
- specific instances
- observable
- the act of kiss/sitting on lap
- Universals(共相):
- abstract notions
- unobservable
- love
- ??既然共相不能被观察,它是怎样被定义出来的呢?比如爱是怎样出现这个概念的呢?是否共相只是人类为了更方便地理解和描述客观现象,而定义的抽象名词??
- Particulars(殊相):
- Idealism(唯心)
- reality in mind,a mental construct
- particulars and universals are both mental representations.
- Materialism(唯物)
- external world independent of our mind
- everything(including our feelings&thoughts) is a result of the interaction of physical stuff
- Realism(现实主义)
- external world independent of our mind
- Platonic Realism
- universals exist independent from our observation on a separate abstract plane
- Scientific Realism
- universals are assumed useful and exist
- Platonic Realism
- external world independent of our mind
- Nominalism(唯名论)
- reality as independent of our mind
- deny the existence of universals
- help make sense of the world
-
-
Epistemology—Study of knowledge
- How can we know it?
- Two types of opinions:
- Rationalism
- Knowledge gained through reasoning
- Plato&Descartes
- Empiricism
- Knowledge gained through sensory experience
- Aristotle&Galileo&Bacon&Hume
- Rationalism
-
-
Approaches
-
Objectivism
-
Psychological and social phenomena are external and independent properties.
-
Approach—Quantitative
- quantifiable observations
- aggregation over subjects
- inference to a larger population
- possibly universal explanation
- quantitative statistical techniques
-
-
Constructism—Ontological view
-
Reality is considered primarily a mental construction that depends on the observer and context.
-
Context/time/culture have influence on the concepts
-
Interpretivism—Epistemological view
- Hermeneutics
- interpret behavior within their social context
- Hermeneutics refers to the philosophy of interpretation and understanding..
- Phenomenology
- investigate the meaning that they attach to the phenomena that they experience.
- Phenomenology is “the philosophical tradition that seeks to understand the world through directly experiencing the phenomena”.
- Verstehen
- empathic understanding of social phenomenon
- Hermeneutics
-
Problems of Constructism
- Layered interpretation
- more chance of misinterpretation
- Lack of comparability of outcomes
- no universal explanations possible
- difference in frame of reference
- hard to find out what the relevant aspects of the social context are
- Layered interpretation
-
Approaches—Qualitative
- unstructured interview/ participatory observation
-
-
-
Goals
-
Type of knowledge
- Universalistic Research
- General explanation
- Particularistic Research
- Specific explanation
- Universalistic Research
-
Type of Goals
- Applied Research
- improve human condition
- Fundamental Research
- for the sake of knowing
- Applied Research
-